MIT Laboratory for Information and Decision Systems (Sunbochen Tang, Navid Azizan, Themistoklis Sapsis) · Physics-constrained Chaos Models
Physically consistent AI models of chaotic systems
Researchers at MIT LIDS present a method that enforces energy dissipation as a hard constraint on machine learning models of chaotic systems. The model learns an energy-like function and a confining boundary, and a projection layer keeps predictions bounded over arbitrarily long forecasts. The team reports that the approach closely matched true outcomes on several physical systems, where conventional models drifted into impossible predictions. The paper is published in PNAS, and the team says it is making the information freely available.
Open the source ↗Similar Research & Safety releases
- Probing the "Conscious" Mind: Selective Access and Global Workspace in Vision-Language Models
Jiahao Huang and Jun Wang, University College London · VLM Interpretability · Week 48, 2026
- Posterior Matching Distillation
NVIDIA (Hidir Yesiltepe, Julius Berner, Arash Vahdat, Pinar Yanardag) · Diffusion distillation · Week 48, 2026
- Test-time adaptation for AI text detectors
MIT and Cornell Tech researchers (Kevin Ren, Manish Raghavan, Nikhil Garg) · Adaptive AI Detector · Week 48, 2026
- LightTAR: Light and Fast Target-Aware Representations for Multimodal Tabular Learning
Eilam Shapira, Alan Arazi, Shoham Grunblat, Roi Reichart (Technion) · Target-aware tabular encoding · Week 48, 2026
- CurvDelta: Low-Curvature Delta Modeling For Surgical Learning and Unlearning
Zeguan Xiao, Zhuocheng Liang, Yun Chen, Yong Wang, Guanhua Chen, Pinyan Lu · Curvature-Constrained Adaptation · Week 48, 2026
- Self-Improving Memory
Meta FAIR · Self-Improving Memory · Week 48, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.